摘要
一位新闻记者-机器人和机器学习的工作人员新闻编辑每日新闻-健康和医学的新研究-临床化学和实验室医学是一篇报道的主题。根据NewsRx编辑在澳大利亚利物浦的新闻报道，这项研究指出：“传统的自动验证规则独立地评估分析物，实际上缺失了表明错误的异常结果模式，如收集管添加剂引起的血清C值。这项研究评估了多种异常检测算法是否能提高对这些错误的检测。”新闻记者从新南威尔士州健康病理学的研究中获得了引用，“多元高斯、k近邻(KNN)距离和一类支持向量机(SVM)异常检测模型，以及常规极限检查，使用127451电解质、UR EA和肌酐(EUC)结果的训练数据集开发。”所有方法的标记率均为5%。将模型与限度检查进行比较，以确定它们从添加了来自检测管的添加剂的样品中检测非典型EUC结果的能力：EDTA、氟化物、柠檬酸钠或柠檬酸葡萄糖（每种污染物n=200）。该研究还评估了模型识别127449单分析物错误的能力。多变量模型的潜在弱点。KNN距离和SVM模型在检测所有污染物方面优于极限检查(P值<0.05)。多变量高斯模型在检测EDTA污染方面没有超过极限检查，但在检测其他添加剂方面优于极限检查。所有模型在识别单一分析物误差方面都超过极限检查，KNN距离模型显示出最高的总体敏感性。多变量异常检测模型，特别是KN N距离模型在检测血清污染和单一分析物误差方面优于传统方法。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Health and Medicine-Clinical Chemistry and Laboratory Medicine is the subject of a report. According to news reporting from Liverpool, Australia, by NewsRx editors, the research st ated, "Conventional autoverification rules evaluate analytes independently, pote ntially missing unusual patterns of results indicative of errors such as serum c ontamination by collection tube additives. This study assessed whether multivari ate anomaly detection algorithms could enhance the detection of such errors." The news correspondents obtained a quote from the research from NSW Health Patho logy, "Multivariate Gaussian, k-nearest neighbours (KNN) distance, and one-class support vector machine (SVM) anomaly detection models, along with conventional limit checks, were developed using a training dataset of 127,451 electrolyte, ur ea, and creatinine (EUC) results, with a 5 % flagging rate targete d for all approaches. The models were compared with limit checks for their abili ty to detect atypical EUC results from samples spiked with additives from collec tion tubes: EDTA, fluoride, sodium citrate, or acid citrate dextrose (n=200 per contaminant). The study additionally assessed the ability of the models to ident ify 127,449 single-analyte errors, a potential weakness of multivariate models. The KNN distance and SVM models outperformed limit checks for detecting all cont aminants (p-values <0.05). The multivariate Gaussian model did not surpass limit checks for detecting EDTA contamination but was superior f or detecting the other additives. All models surpassed limit checks for identify ing single-analyte errors, with the KNN distance model demonstrating the highest overall sensitivity. Multivariate anomaly detection models, particularly the KN N distance model, were superior to the conventional approach for detecting serum contamination and single-analyte errors."
NETL
NSTL